Book Recommendation Based on Heterogeneous Network Representation Learning

doi:10.3778/j.issn.1002-8331.2010-0383

Abstract

Abstract: This paper plans to expand and integrate various book features and relationships, improves the accuracy and diversity of book recommendation from the semantic-related perspective, and explores the contribution and impact of different book features on recommendation. Firstly, book features are extracted to build the book heterogeneous network, and the multidimensional relationships between features are define. Then, a variety of book features are combined to form the semantic vector representation of the book based on heterogeneous network representation learning, and the related books are recommended by calculating the semantic correction between vectors based on a selected similarity calculation index. Finally, the accuracy of results is evaluated by RMSE and MAE, and the diversity of the results are evaluated by variety, balance and disparity. The Amazon book dataset is extended by multiple features, such as author, keyword and publisher, to construct the book heterogeneous network. The empirical result shows that RMSE and MAE are respectively reduced by 19.52%, 20.51% mostly comparing with the collaborative filtering algorithm. RMSE and MAE also are respectively reduced by 0.17% and 2.9% mostly comparing with the deepwalk. This method can effectively improve the accuracy of recommendation. The indicators of diversity show that this recommend books are more kinds of category and rich in content, this method also improves the diversity. And this paper clarifies the contribution of different features on recommendation, in descending order of contribution: author, keyword, category, user and publisher.

Key words: book recommendation, network representation learning, book heterogeneous network

摘要： 扩展和综合利用多种图书特征及其关联关系，从语义相关的角度提高图书推荐的准确性和多样性，探索不同特征对于图书推荐的贡献程度和影响。抽取多种图书特征构建图书异构网络并设计形成特征间的多维关联关系。引入异构网络表示学习方法，融合多种图书特征，形成图书的语义向量表示，选取向量相似度指标计算并表示图书间的语义相关程度，实现相关图书推荐。利用平均绝对误差、均方根误差等定量指标评估推荐的准确性，利用丰富度、均衡性、差异度等指标分析图书推荐的多样性。扩展亚马逊图书数据集，增加作者、关键词和出版社等特征项构建图书异构网络。实证结果表明，相较于协同过滤，该方法的均方根误差、平均绝对误差最多分别降低了19.52%和20.51%，相较于deepwalk方法，该方法在均方根误差、平均绝对误差最多分别降低了0.17%和2.9%，准确性得到较大提高；多样性评测指标也显示该方法推荐的图书种类更多元、内容更丰富，多样性同样得到了提高；明晰了不同特征对图书推荐的贡献程度，从高到低依次为作者、关键词、类别、购买者和出版社。

关键词: 图书推荐, 网络表示学习, 图书异构网络

ZHANG Jinzhu, JIANG Linqi, WANG Yue, KONG Jie, GAO Yang. Book Recommendation Based on Heterogeneous Network Representation Learning[J]. Computer Engineering and Applications, 2022, 58(9): 263-270.

张金柱, 蒋霖琪, 王玥, 孔捷, 高扬. 基于异构网络表示学习的相关图书推荐研究[J]. 计算机工程与应用, 2022, 58(9): 263-270.

References

[1] 曾云华，江伟.基于Lib2.0的图书信息过载解决方案[J].图书馆，2012，1（3）：117-118.
ZENG Y H，JIANG W.Solutions based on Lib2.0 of book information overload[J].Library，2012，1（3）：117-118.
[2] 刘书芬.近十年高校图书馆图书推荐研究综述[J].韶关学院学报，2013，34（7）：201-205.
LIU S F.A study of university library book recommendation in recent ten years[J].Journal of Shaoguan University，2013，34（7）：201-205.
[3] 涂存超，杨成，刘知远，等.网络表示学习综述[J].中国科学：信息科学，2017，47（8）：980-996.
TU C C，YANG C，LIU Z Y，et al.Network representation learning：an overview[J].Scientia Sinica：Informationis，2017，47（8）：980-996.
[4] MOONEY R J，ROY L.Content-based book recommending using learning for text categorization[C]//Proceedings of the Fifth ACM Conference on Digital Libraries，Texas，USA，2-7 Jun，2000：195-204.
[5] LOPS P，GEMMIS M D，SEMERARO G.Content-based recommender systems：state of the art and trends[M]//Recommender systems handbook.USA：Springer，2011：73-105.
[6] 奉国和，梁晓婷.协同过滤推荐研究综述[J].图书情报工作，2011，55（16）：126-130.
FENG G H，LIANG X T.Review of collaborative filtering recommender[J].Library and Information Service，2011，55（16）：126-130.
[7] AGRAWAL R.Mining association rules between sets of items in large databases[C]//Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data，New York，USA，26-28 May，1993：207-216.
[8] PEROZZI B，AL-RFOU R，SKIENA S.Deepwalk：online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，New York，USA，24-27 Aug，2014：701-710.
[9] GROVER A，LESKOVEC J.Node2vec：scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining，San Francisco，USA，24-27 Aug，2016：1-10.
[10] YU X，REN X，SUN Y，et al.Personalized entity recommendation：a heterogeneous information network approach[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining，New York，USA，24-28 Feb，2014：283-292.
[11] ZHAO W X，HUANG J，WEN J R.Learning distributed representations for recommender systems with a network embedding approach[C]//Asia Information Retrieval Symposium（AIRS），Beijing，China，30 Nov-2 Dec，2016：224-236.
[12] ZHANG C，YU L，WANG Y，et al.Collaborative user network embedding for social recommender systems[C]//Proceedings of the 2017 SIAM International Conference on Data Mining，Texas，USA，27-29 Apr，2017：381-389.
[13] SHI C，HU B，ZHAO W X，et al.Heterogeneous information network embedding for recommendation[J].IEEE Transactions on Knowledge and Data Engineering，2019，31（2）：357-370.
[14] 李树青，庄光光，秦嘉杭，等.借阅场景下图书专业性质量测度方法和图书个性化推荐服务方法[J].图书情报工作，2018，62（11）：53-63.
LI S Q，ZHUANG G G，QIN J H，et al.The method of measuring the professional quality of books and personalized book recommendation service in circulating scene[J].Library and Information Service，2018，62（11）：53-63.
[15] 许海云，尹春晓，郭婷，等.学科交叉研究综述[J].图书情报工作，2015，59（5）：119-127.
XU H Y，YIN C X，GUO T，et al.Interdisciplinary research review[J].Library and Information Service，2015，59（5）：119-127.
[16] ROSE S，ENGEL D，CRAMER N，et al.Automatic keyword extraction from individual documents[M]//Text mining：applications and theory.Hoboken：John Wiley & Sons，Ltd，2010：3-20.